[Intel-gfx] [PATCH] drm/i915: Reduce locking in command submission

Tvrtko Ursulin tvrtko.ursulin at linux.intel.com
Thu Jan 15 09:05:30 PST 2015


On 01/15/2015 04:54 PM, Ben Widawsky wrote:
> On Thu, Jan 15, 2015 at 11:21:30AM +0000, Tvrtko Ursulin wrote:
>> From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
>>
>> This eliminates six needless spin lock/unlock pairs when writing out ELSP. Apart
>> from tidier code main benefit is between 0.51% and 0.73% speedup on some OGL
>> tests under CHV (bench_OglBatch4 bench_OglDeferred respectively).
>
> With 95% confidence t-test on n=5
>
>>
>> Kindly benchmarked by Ben Widawsky.
>
> FWIW, as I mentioned on IRC, I think the reduction of the unnecessary forcewake
> (someone should fix the shadow register list) is probably more beneficial than
> removing the spin on an uncontested lock. I was tempted to try that myself, but
> I didn't have time or much interest since your patch accomplishes the same
> thing.

I missed that IRC discussion, but I don't think it was doing forcewakes 
since the outer block in execlists_elsp_write bumps the counters which 
made I915_WRITE & co skip them.

Regards,

Tvrtko


More information about the Intel-gfx mailing list